I am ready for a long road flight for work with a week- or months-long projects.
Contact us
Cookies
Cookie Settings
Cookies necessary for the correct operation of the site are always enabled.
Other cookies are configurable.
Other cookies are configurable.
Data processing algorithms
Platform
Standardisation of multitude of unstructured data
If you get stuck by the time and staff investment to tackle overwhelming amounts of unstructured data from wearables - we are here to help!
Wearables already generate lots of data that could help detect early signs and monitor chronic conditions. Unfortunately, large variability in data format and data quality are a time-consuming barrier for clinicians and researchers to incorporate these data in their analytical work and decision making.
Our toolkit was designed to standardize unstructured data in a universal, convenient and easy-to-use format.
Wearables already generate lots of data that could help detect early signs and monitor chronic conditions. Unfortunately, large variability in data format and data quality are a time-consuming barrier for clinicians and researchers to incorporate these data in their analytical work and decision making.
Our toolkit was designed to standardize unstructured data in a universal, convenient and easy-to-use format.
Missing data
Impute short periods missing data
Data resolution
Works with resolution from 1/min to 1/15min
Device-agnostic technology enables simultaneous analysis of data form devices of different manufacturers
Hardware-free
Notify long periods of low quality or missing data
Low quality data
Mismatching data
Time-zone correction fixes steps, bpm, and sleep data mismatches
Heart rate and step counts
Both Step counts-only data and parallel streams of steps and bpm
Feature-extraction neural network algorithm adjusts for manufacturer, os version, and wearing style
Deep-learning